Breezeblue vs Anthropic vs DeepSeek vs Microsoft

Head to head on 17 boards: Anthropic places best on 13, DeepSeek places best on 3, Breezeblue places best on 1 and Microsoft places best on 0. All 4 ranked on 0 of 26 boards.

Two at a time on this screen. Tap one to swap it in.

BBreezeblueAnthropicDeepSeekMicrosoft

Board	Read	BBreezeblue	Anthropic	DeepSeek	Microsoft
Chat2
Text ArenaArena ratingtodaytoday	Nov 10todaytoday		#41,506best of the pickedClaude Opus 5.5	#321,475DeepSeek V4.1 Flash
MultiChallengeScoretodaytoday	Nov 10todaytoday		#1067.7%Claude Haiku 5.5	#574.9%best of the pickedDeepSeek V4P1 Flash
Reasoning7
MMLU-ProAccuracy · staletodaytoday	Nov 10todaytoday		#489.1%best of the pickedClaude Opus 4.6	#3385.0%DeepSeek-V3.2	#7576.0%Phi 4 Plus
AA IntelligenceIndextodaytoday	Nov 10todaytoday		#164.6best of the pickedClaude Fable 5.2	#1732.6DeepSeek V4.1 Flash
Epoch ECIECItodaytoday	Nov 10todaytoday		#1174.2best of the pickedClaude Fable 5.2	#21159.3DeepSeek V4.1 Flash
LiveBenchGlobal averagetodaytoday	Nov 10todaytoday		#183.4%best of the pickedClaude Fable 5.1	#881.1%DeepSeek V4.1 Flash
GPQA DiamondAccuracytodaytoday	Nov 10todaytoday		#395.6%best of the pickedClaude Sonnet 5.5	#2293.2%DeepSeek V4.1 Flash
ARC-AGI-2Scoretodaytoday	Nov 10todaytoday		#393.8%best of the pickedClaude Fable 5.2	#2078.1%DeepSeek V4.1 Flash
HLEAccuracytodaytoday	Nov 10todaytoday		#246.5%Claude Fable 5.1
Coding4
WebDev ArenaArena ratingtodaytoday	Nov 10todaytoday		#11,818best of the pickedClaude Opus 5.5	#141,664DeepSeek V4.1 Flash
SWE-bench VerifiedResolved · staletodaytoday	Nov 10todaytoday		#176.8%best of the pickedClaude Opus 4.5	#1170.0%DeepSeek-V3.2
Aider PolyglotPass rate · staletodaytoday	Nov 10todaytoday		#1072.0%Claude Opus 4	#874.2%best of the pickedDeepSeek-V3.2
SWE-Bench ProResolvedtodaytoday	Nov 10todaytoday		#198.0%Claude Opus 5
Agents and tools3
BFCLOverall accuracy · staletodaytoday	Nov 10todaytoday		#177.5%best of the pickedClaude Opus 4.5	#1256.7%DeepSeek-V3.2	#5028.8%Phi 4
MCP AtlasPass ratetodaytoday	Nov 10todaytoday		#387.2%Claude Fable 5.1
Search ArenaArena ratingtodaytoday	Nov 10todaytoday		#51,229Claude Fable 5
Vision2
Vision ArenaArena ratingtodaytoday	Nov 10todaytoday		#11,309best of the pickedClaude Fable 5	#351,263DeepSeek V4.1 Flash
Document ArenaArena ratingtodaytoday	Nov 10todaytoday		#11,500Claude Fable 5
Image2
Image EditArena ratingtodaytoday	Nov 10todaytoday				#41,468MAI Image 2.7
Text-to-ImageArena ratingtodaytoday	Nov 10todaytoday				#61,329MAI Image 2.6
Speech2
Speech ArenaArena ratingtodaytoday	Nov 10todaytoday	#131,228best of the pickedBreeze TTS 2			#311,144Azure Hd 2.5
Open ASRAverage WERtodaytoday	Nov 10todaytoday				#35.55 WERazure-speech-09-2026 (microsoft)
Embeddings1
MTEBMean task scoretodaytoday	Nov 10todaytoday				#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedtodaytoday	Nov 10todaytoday		#931 tok/sbest of the pickedClaude Sonnet 5.5	#1323 tok/sDeepSeek V4 Pro 0813
Price1
AA PriceBlended pricetodaytoday	Nov 10todaytoday		#1$0.20best of the pickedClaude Haiku 5.5	#4$0.53DeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokenstodaytoday	Nov 10todaytoday		#66.7T tokClaude Opus 5.5	#155.4T tokbest of the pickedDeepSeek V4.1 Flash

Green marks the best placing among the picked where two or more are ranked; ties are marked for each. Ranks are each board's own order (lower is better), scores as the board published them. Dash: not on that board.